fix(deps): update dependency sqlglot to >=23.4,<25.21 (#10050)

Co-authored-by: renovate[bot] <29139614+renovate[bot]@users.noreply.github.com>
Co-authored-by: Phillip Cloud <[email protected]>

ibis/backends/sql/compilers/impala.py

@@ -295,6 +295,9 @@ def visit_Date(self, op, *, arg):
     def visit_RegexReplace(self, op, *, arg, pattern, replacement):
         return self.f.regexp_replace(arg, pattern, replacement, dialect=self.dialect)
 
+    def visit_RegexExtract(self, op, *, arg, pattern, index):
+        return self.f.anon.regexp_extract(arg, pattern, index)
+
     def visit_Round(self, op, *, arg, digits):
         rounded = self.f.round(*filter(None, (arg, digits)))
 

ibis/backends/sql/compilers/snowflake.py

@@ -424,13 +424,7 @@ def visit_ArrayPosition(self, op, *, arg, other):
 
     def visit_RegexExtract(self, op, *, arg, pattern, index):
         # https://docs.snowflake.com/en/sql-reference/functions/regexp_substr
-        return sge.RegexpExtract(
-            this=arg,
-            expression=pattern,
-            position=sge.convert(1),
-            group=index,
-            parameters=sge.convert("ce"),
-        )
+        return self.f.anon.regexp_substr(arg, pattern, 1, 1, "ce", index)
 
     def visit_ArrayZip(self, op, *, arg):
         return self.if_(

ibis/backends/sql/dialects.py

@@ -205,6 +205,7 @@ def new_name(names: set[str], name: str) -> str:
 
 class Flink(Hive):
     UNESCAPED_SEQUENCES = {"\\\\d": "\\d"}
+    REGEXP_EXTRACT_DEFAULT_GROUP = 0
 
     class Generator(Hive.Generator):
         UNNEST_WITH_ORDINALITY = False
@@ -308,6 +309,7 @@ class Tokenizer(Hive.Tokenizer):
 
 class Impala(Hive):
     NULL_ORDERING = "nulls_are_large"
+    REGEXP_EXTRACT_DEFAULT_GROUP = 0
 
     class Generator(Hive.Generator):
         TRANSFORMS = Hive.Generator.TRANSFORMS.copy() | {

ibis/backends/tests/test_string.py

@@ -1257,11 +1257,6 @@ def string_temp_table(backend, con):
                     raises=AssertionError,
                     reason="Spark SQL LTRIM doesn't accept characters to trim",
                 ),
-                pytest.mark.notimpl(
-                    ["bigquery", "snowflake"],
-                    raises=AssertionError,
-                    reason="does a full `strip` instead",
-                ),
             ],
         ),
         param(
@@ -1274,11 +1269,6 @@ def string_temp_table(backend, con):
                     raises=AssertionError,
                     reason="Spark SQL RTRIM doesn't accept characters to trim",
                 ),
-                pytest.mark.notimpl(
-                    ["bigquery", "snowflake"],
-                    raises=AssertionError,
-                    reason="does a full `strip` instead",
-                ),
             ],
         ),
         param(

pyproject.toml

@@ -41,7 +41,7 @@ atpublic = ">=2.3,<6"
 parsy = ">=2,<3"
 python-dateutil = ">=2.8.2,<3"
 pytz = ">=2022.7"
-sqlglot = ">=23.4,<25.20"
+sqlglot = ">=23.4,<25.21"
 toolz = ">=0.11,<1"
 typing-extensions = ">=4.3.0,<5"
 numpy = { version = ">=1.23.2,<3", optional = true }

requirements-dev.txt

@@ -257,7 +257,7 @@ sortedcontainers==2.4.0 ; python_version >= "3.10" and python_version < "4.0"
 soupsieve==2.6 ; python_version >= "3.10" and python_version < "3.13"
 sphobjinv==2.3.1.1 ; python_version >= "3.10" and python_version < "3.13"
 sqlalchemy==2.0.32 ; python_version >= "3.10" and python_version < "3.13"
-sqlglot==25.19.0 ; python_version >= "3.10" and python_version < "4.0"
+sqlglot==25.20.1 ; python_version >= "3.10" and python_version < "4.0"
 stack-data==0.6.3 ; python_version >= "3.10" and python_version < "4.0"
 statsmodels==0.14.2 ; python_version >= "3.10" and python_version < "3.13"
 tabulate==0.9.0 ; python_version >= "3.10" and python_version < "3.13"